摘要
针对无人机(UAV)视频数据集采集成本高,现有数据普遍存在规模有限、应用场景单一,且现有无监督目标跟踪方法通常只用于通用数据集设计,对UAV的复杂场景难以学习可靠信息等问题,提出一种无监督UAV目标跟踪模型,其基于时间周期一致性与动态记忆增强。首先,将显著性目标检测引入无标签的对象发现,并与无监督光流技术结合,引入基于图像熵的动态规划,提高伪标签的质量。其次,为视频中的每一帧定义权重,并利用这些权重进行单帧训练,以更全面地利用每一帧的信息。最后,借鉴长短期记忆网络的思想,将记忆队列转变为动态记忆队列。设计自注意力分支且作为记忆队列的门控机制,并控制队列的记忆与遗忘,在不增加队列长度的同时,实现长跨度下的目标特征变化学习。该方法在UAV数据集上的准确率达到了68%,领先于其他无监督跟踪器,与一般有监督跟踪器的性能持平。在一般场景数据集上也与其他无监督跟踪器性能近似,准确率达到77%。在UAV数据集和一般场景数据集上的实验结果表明,其在快速运动和大尺度变化场景性能方面有较好提高。
The collection of UAV(unmanned aerial vehicle)video datasets is costly and faces issues such as limited quantity,low quality,and scenario constraints.To address these challenges,an unsupervised UAV-object-tracking model based on temporal cycle consistency and dynamic memory enhancement was proposed.First,salient-object detection was introduced for unlabeled object discovery.By combining salient object detection with unsupervised optical flow techniques and incorporating dynamic programming based on image entropy,the quality of pseudo-labels was improved.Second,a weight is defined for each frame in the video,and these weights are utilized for single-frame training to fully leverage the information from all frames.Finally,inspired by long short-term memory(LSTM)networks,the memory queue was transformed into a dynamic memory queue,along with a self-attention branch designed to control its updates.Target-features changes over long spans were learned without increasing the queue length.The proposed method achieved 68%accuracy on UAV datasets,outperforming other unsupervised trackers and matching typical supervised-tracker performance.On general scene datasets,it attained 77%accuracy,comparable to other unsupervised trackers.Experimental results on both UAV and general scene datasets demonstrated that the proposed method achieved excellent performance in scenarios involving rapid motion and large-scale variations.
作者
肖凯
袁玲
储珺
XIAO Kai;YUAN Ling;CHU Jun(Jiangxi Provincial Key Laboratory of Image Processing and Pattern Recognition,Nanchang Hangkong University,Nanchang Jiangxi 330063,China;School of Software Engineering,Nanchang Hangkong University,Nanchang Jiangxi 330063,China)
出处
《图学学报》
北大核心
2025年第6期1281-1291,共11页
Journal of Graphics
基金
江西省研究生创新专项(YC2023-S747)。
关键词
目标跟踪
无人机
无监督学习
注意力机制
孪生网络
object tracking
unmanned aerial vehicle
unsupervised learning
attention mechanism
twin network
